← Learning Types
Machine Learning › Learning Types ›

Active Learning

1885 directly classified papers

Papers per year

Papers

Teaching Active Human Learners AAAI 2021
Incorporating Unlabeled Data into Distributionally Robust Learning JMLR 2021
Efficient Video Annotation With Visual Interpolation and Frame Selection Guidance WACV 2021
Actively Learning Concepts and Conjunctive Queries under ELr-Ontologies IJCAI 2021
Meta-Learning Effective Exploration Strategies for Contextual Bandits AAAI 2021
Active Bayesian Assessment of Black-Box Classifiers AAAI 2021
Improved Algorithms for Efficient Active Learning Halfspaces with Massart and Tsybakov Noise COLT 2021
Locality Sensitive Teaching NIPS 2021
Dynabench: Rethinking Benchmarking in NLP NAACL 2021
Cost-Effective Interactive Attention Learning with Neural Attention Processes ICML 2020
Fiduciary Bandits ICML 2020
Ready Policy One: World Building Through Active Learning ICML 2020
Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles ICML 2020
Optimizing Data Usage via Differentiable Rewards ICML 2020
Confidence-Aware Learning for Deep Neural Networks ICML 2020
Active Learning on Attributed Graphs via Graph Cognizant Logistic Regression and Preemptive Query Generation ICML 2020
Thompson Sampling via Local Uncertainty ICML 2020
Neural Contextual Bandits with UCB-based Exploration ICML 2020
Preselection Bandits ICML 2020
Active Adversarial Domain Adaptation WACV 2020
Active Learning for Imbalanced Datasets WACV 2020
TrueLearn: A Family of Bayesian Algorithms to Match Lifelong Learners to Open Educational Resources AAAI 2020
ActiveThief: Model Extraction Using Active Learning and Unannotated Public Data AAAI 2020
Deep Reinforcement Learning for Active Human Pose Estimation AAAI 2020
Learning to Auto Weight: Entirely Data-Driven and Highly Efficient Weighting Framework AAAI 2020